Spectrum sensing is an essential function of cognitive radio technology. The secondary users use it to enable the reuse of available radio resources without harming licensed users. Several approaches based on Artificial Intelligence (AI), Machine Learning (ML), Federated Learning (FL), stochastic approaches, and many others have recently been proposed to perform and evaluate the impact of Spectrum Sensing to Cognitive Radio. Specifically, cooperative spectrum sensing can be considered a key technology to improve the performance of spectrum sensing at low signal-to-noise ratios.
The goal of this Research Topic is to improve the accuracy, reliability, efficiency, and security of spectrum sensing by applying cooperative spectrum sensing algorithms, techniques, models, and protocols. This could be done by using ML methods for real-world data in different environments, experimental validation, and theoretical analyses. Security is another aspect that can also be explored to ensure the integrity of cooperative spectrum sensing. Recent studies have suggested incorporating FL to reduce the communication overhead from sending the training data to the Fusion Center (FC). On the other hand, a proper design of infrastructures, protocols and their implementation is a key point for generating high level quality applications based on spectrum sensing. Therefore, we encourage submitting research papers that explore AI techniques in cooperative spectrum sensing as well as modelling approaches (both simulative and analytical) for applications of it, with particular attention their dependability (e.g. availability, reliability, performance, security).
This Research Topic aims to explore the latest research advances in developing and comparing cooperative spectrum sensing techniques, pointing out any support of AI, ML, FL, analytical and simulative modelling to solve this issue and highlighting the advantages and disadvantages of performance, dependability, complexity, and possible real-time applications.
Specific topics may include but are not limited to:
• Enhanced spectrum awareness
• Improved spectrum efficiency
• Reliable secondary user access
• Spectrum mobility and adaptation
• Dynamic spectrum access in TV white spaces
• Dynamic spectrum management
• Interference mitigation
• Stochastic modelling of spectrum sensing based applications
• Functional and non-functional metrics of CR applications
• Security of Cooperative Spectrum Sensing techniques
Keywords:
Spectrum sensing, Cognitive Radio, Artificial intelligence, Machine Learning
Important Note:
All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.
Spectrum sensing is an essential function of cognitive radio technology. The secondary users use it to enable the reuse of available radio resources without harming licensed users. Several approaches based on Artificial Intelligence (AI), Machine Learning (ML), Federated Learning (FL), stochastic approaches, and many others have recently been proposed to perform and evaluate the impact of Spectrum Sensing to Cognitive Radio. Specifically, cooperative spectrum sensing can be considered a key technology to improve the performance of spectrum sensing at low signal-to-noise ratios.
The goal of this Research Topic is to improve the accuracy, reliability, efficiency, and security of spectrum sensing by applying cooperative spectrum sensing algorithms, techniques, models, and protocols. This could be done by using ML methods for real-world data in different environments, experimental validation, and theoretical analyses. Security is another aspect that can also be explored to ensure the integrity of cooperative spectrum sensing. Recent studies have suggested incorporating FL to reduce the communication overhead from sending the training data to the Fusion Center (FC). On the other hand, a proper design of infrastructures, protocols and their implementation is a key point for generating high level quality applications based on spectrum sensing. Therefore, we encourage submitting research papers that explore AI techniques in cooperative spectrum sensing as well as modelling approaches (both simulative and analytical) for applications of it, with particular attention their dependability (e.g. availability, reliability, performance, security).
This Research Topic aims to explore the latest research advances in developing and comparing cooperative spectrum sensing techniques, pointing out any support of AI, ML, FL, analytical and simulative modelling to solve this issue and highlighting the advantages and disadvantages of performance, dependability, complexity, and possible real-time applications.
Specific topics may include but are not limited to:
• Enhanced spectrum awareness
• Improved spectrum efficiency
• Reliable secondary user access
• Spectrum mobility and adaptation
• Dynamic spectrum access in TV white spaces
• Dynamic spectrum management
• Interference mitigation
• Stochastic modelling of spectrum sensing based applications
• Functional and non-functional metrics of CR applications
• Security of Cooperative Spectrum Sensing techniques
Keywords:
Spectrum sensing, Cognitive Radio, Artificial intelligence, Machine Learning
Important Note:
All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.